© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10035
    Prev
    Next
    INDEX
    Explanations

    format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ose
    -0.07
    é¢ľ
    -0.07
    åĴĮåŃ¦æł¡
    -0.07
    eby
    -0.07
    à¸Ħร
    -0.07
    æĬĢæľ¯åĬĽéĩı
    -0.07
    ãģĹãĤĤ
    -0.07
    arly
    -0.06
    ×IJ×ķת
    -0.06
    à¸Ĺ
    -0.06
    POSITIVE LOGITS
    å±ħå¤ļ
    0.10
     predomin
    0.09
    æĦıåij³çĿĢ
    0.08
    ä¸ĭçļĦ
    0.08
    Ñģад
    0.07
    èĪİ
    0.07
    weise
    0.07
    ű
    0.07
    ingle
    0.07
    iance
    0.07
    Activations Density 0.340%

    No Known Activations